fenix
/
ytdl-nightly
mirror of https://github.com/ytdl-org/ytdl-nightly.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1301 from rzhxeo/xhamster 

XHamsterIE: Fix video extension and add video description
This commit is contained in:
Jaime Marquínez Ferrándiz 2013-08-23 17:21:30 +02:00
parent d4051a8e05 4353cf51a0
commit 53b0f3e4e2
1 changed files with 9 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
youtube_dl/extractor/xhamster.py
View File

@ -3,7 +3,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urllib_parse, compat_urllib_parse,
unescapeHTML,
ExtractorError, ExtractorError,
) )
@ -36,15 +36,17 @@ class XHamsterIE(InfoExtractor):
video_url = compat_urllib_parse.unquote(mobj.group('file')) video_url = compat_urllib_parse.unquote(mobj.group('file'))
else: else:
video_url = mobj.group('server')+'/key='+mobj.group('file') video_url = mobj.group('server')+'/key='+mobj.group('file')
video_extension = video_url.split('.')[-1] video_extension = video_url.split('.')[-1].split('?')[0]
video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>',
webpage, u'title') webpage, u'title')
# Can't see the description anywhere in the UI # Only a few videos have an description
# video_description = self._html_search_regex(r'<span>Description: </span>(?P<description>[^<]+)', mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage)
# webpage, u'description', fatal=False) if mobj:
# if video_description: video_description = unescapeHTML(video_description) video_description = unescapeHTML(mobj.group('description'))
else:
video_description = None
mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage) mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
if mobj: if mobj:
@ -64,7 +66,7 @@ class XHamsterIE(InfoExtractor):
'url': video_url, 'url': video_url,
'ext': video_extension, 'ext': video_extension,
'title': video_title, 'title': video_title,
# 'description': video_description, 'description': video_description,
'upload_date': video_upload_date, 'upload_date': video_upload_date,
'uploader_id': video_uploader_id, 'uploader_id': video_uploader_id,
'thumbnail': video_thumbnail 'thumbnail': video_thumbnail